Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.4110. Min Act: -0.0000

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3222. Min Act: -0.0000

Data Index: 443840 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.2572. Min Act: -0.0000

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.2015. Min Act: -0.0000

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1298721 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.2304. Min Act: -0.0000

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.1045. Min Act: -0.0000

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9685. Min Act: -0.0000

Data Index: 74481 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9833. Min Act: -0.0000

Data Index: 190271 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8982. Min Act: -0.0000

Data Index: 869671 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9370. Min Act: -0.0000

Data Index: 707901 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9591. Min Act: -0.0000

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8978. Min Act: -0.0000

Data Index: 969995 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9136. Min Act: -0.0000

Data Index: 637877 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8395. Min Act: -0.0000

Data Index: 130530 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8705. Min Act: -0.0000

Data Index: 585458 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1303299 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8198. Min Act: -0.0000

Data Index: 948802 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1045004 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8109. Min Act: -0.0000

Data Index: 59998 (C4 (Web Text))

Max Activating Token Index: 439